Upload 8 files

README.md

@@ -10,4 +10,4 @@ pinned: false
 license: apache-2.0
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+Check out the configuration reference at <https://huggingface.co/docs/hub/spaces-config-reference>

app.py

@@ -0,0 +1,39 @@
+import streamlit as st
+import pandas as pd
+import streamlit.components.v1 as components
+
+st.sidebar.image("images/logo.png", use_column_width=True)
+st.sidebar.write("Bunka Summarizes & Visualizes Information as Maps using LLMs.")
+st.sidebar.title("Github Page")
+st.sidebar.write(
+    "Have a look at the following package on GitHub: https://github.com/charlesdedampierre/BunkaTopics"
+)
+st.sidebar.title("Dataset")
+st.sidebar.write(
+    "We used a subset of Wikipedia dataset: https://huggingface.co/datasets/OpenAssistant/oasst2"
+)
+
+st.title("How to understand large textual datasets?")
+
+df = pd.read_csv("data/data_sample.csv", index_col=[0])
+df = df[["message_id", "text"]]
+df = df.head(300)
+st.dataframe(df, use_container_width=True)
+st.title("Inside the OASST2 dataset")
+element = open("images/map_prompt.html", "r", encoding="utf-8")
+
+components.html(element.read(), height=900, width=900)
+
+st.title("Some insights by territory")
+df_info = pd.read_csv("data/topics_info.csv", index_col=[0])
+df_info = df_info[["name", "size", "percent"]]
+df_info["percent"] = df_info["percent"].apply(lambda x: str(int(x)) + "%")
+df_info = df_info.reset_index(drop=True)
+
+st.dataframe(df_info, use_container_width=True)
+
+st.title("Bunka Exploration Engine")
+st.image(
+    "images/pipeline.png",
+    use_column_width=True,
+)